The question about the different between darknet-yolo2 and caffe-yolo9000 about caffe-yolo9000 HOT 9 CLOSED

@OPPOA113

I do not get the high mAP.

you should check the train data(the data and label are wrong)

from caffe-yolo9000.

1. It is the difference between caffe and darknet. Gradient is added in caffe, but it is subtracted in darknet.
2. I didn't add the reorg layer temporarily. I guess that maybe it is your problem.

from caffe-yolo9000.

1. I use the model that you release:gnet_yolo_region_darknet_v3_pretrain_rectify_iter_200000.caffemodel, and test the mAP in voc2007 test dataset , and the mAP is much lower than the darknet yolo2(55% vs 72%). Do you test the mAP on voc2007.
2. I retrain the model caffeyolo9000, and the result is lower. (train data :voc07+12,test data:voc07). I do not use the pretraining model(gnet_yolo_region_darknet_v3_pretrain_iter_600000.caffemodel), because i do not have the model. Could you support the model? Do the pretraining model lead to the low mAP?

Thank you!

from caffe-yolo9000.

1. I have been finding where is the problem which results in low mAP.
2. Pre-trained model is important, it refers to #4.

from caffe-yolo9000.

Thanks you for reply!

1.Could you show the details of the problem which results in low mAP, if you convenience, or share the code in github?

2. Do you get convergence when add the reorg layer ？

Thank you!

from caffe-yolo9000.

Details are all in the original repository. But I have to delete it for some reasons. I haven't add the reorg layer. I would tell you if I get a high mAP with reorg layer next week.

from caffe-yolo9000.

@choasup

Do you add reorg layer and get a high mAP?

from caffe-yolo9000.

@chengshuai @choasup
can you get a high mAp now？
i train my own data,but i can run successfully. some values bacame Nan or something like 0.0000000

from caffe-yolo9000.

@choasup
void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY) { int i; for(i = 0; i < N; ++i) Y[i*INCY] += ALPHA*X[i*INCX]; }
Sorry, in this function, is the gradient is added in darknet? Or if defferent with caffe, where is it in darknet?Thx!

from caffe-yolo9000.